Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    column descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    되
    0.66
     apoi
    0.62
     (
    0.61
     и
    0.61
    이지만
    0.61
    цию
    0.60
    と
    0.59
    ვით
    0.59
     και
    0.59
    т
    0.57
    POSITIVE LOGITS
    h
    0.66
    mallow
    0.64
    ні
    0.63
    methanol
    0.63
    abbing
    0.62
    s
    0.61
    ruary
    0.61
    lusconi
    0.60
    hhhh
    0.59
    mesinin
    0.59
    Act Density 0.001%

    No Known Activations